Agentic
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Agentic tool-use | Agentic Macro-aggregate | Pass@170.3 | 22 | |
| CS research tasks | Agentic 200-prompt (held-out test) | Mean@30.632 | 3 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Agentic tool-use | Agentic Macro-aggregate | Pass@170.3 | 22 | |
| CS research tasks | Agentic 200-prompt (held-out test) | Mean@30.632 | 3 |